A Diffusion Policy checkpoint trained in LeRobot to push a T-shaped block into a target pose in the 2D PushT simulation.
lerobot/act_aloha_sim_transfer_cube_human
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelImitation policy52M paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.Apache 2.0Bimanual
About
An Action Chunking Transformer policy trained in LeRobot on human demonstrations of the simulated ALOHA bimanual cube-transfer task.
Why it matters for physical AI
ACT is the default small imitation-learning policy for low-cost arms, and this checkpoint is a reference for checking that a training setup works.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download lerobot/act_aloha_sim_transfer_cube_humanUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.